© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11719
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to digital marketing, online publishing and technology

    oai_token-act-pair · gemini-2.0-flash

    data attributes or identifiers

    np_token-act-pair-logits · gpt-4o-mini

    Online resources

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WithIOException
    -0.82
     Agamemnon
    -0.71
    principalTable
    -0.68
     myſelf
    -0.66
     itſelf
    -0.66
    contentLoaded
    -0.66
    PerformLayout
    -0.65
     themſelves
    -0.65
     otomatig
    -0.63
     $_[
    -0.62
    POSITIVE LOGITS
     AttributeSet
    0.53
    RESUMO
    0.50
     e
    0.48
     Summit
    0.48
     Signals
    0.48
    itemBuilder
    0.48
    исленность
    0.46
     biệt
    0.45
     signal
    0.45
    FieldNumber
    0.44
    Activations Density 1.544%

    No Known Activations